ComfyUI > Nodes > ComfyUI-NAG-Extended > NAGCFGGuider

ComfyUI Node: NAGCFGGuider

Class Name

NAGCFGGuider

Category
sampling/custom_sampling/guiders
Author
BigStationW (Account age: 367days)
Extension
ComfyUI-NAG-Extended
Latest Updated
2026-05-02
Github Stars
0.03K

How to Install ComfyUI-NAG-Extended

Install this extension via the ComfyUI Manager by searching for ComfyUI-NAG-Extended
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-NAG-Extended in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

NAGCFGGuider Description

Specialized node for AI art generation, offering refined control over sampling process with unique NAG parameters adjustment.

NAGCFGGuider:

The NAGCFGGuider is a specialized node designed to enhance the sampling process in AI art generation by integrating advanced guidance techniques. Its primary purpose is to provide a more refined control over the sampling process, allowing for the generation of high-quality images with specific artistic styles or features. By leveraging the NAG (Negative Aesthetic Guidance) parameters, this node offers a unique capability to adjust the influence of negative conditioning, thereby enabling artists to fine-tune the balance between desired and undesired elements in their creations. The NAGCFGGuider is particularly beneficial for users looking to achieve precise artistic outcomes, as it allows for the manipulation of various parameters that influence the final image's aesthetic quality. This node is essential for artists who wish to explore and experiment with different styles and effects, providing them with the tools to push the boundaries of their creative expression.

NAGCFGGuider Input Parameters:

model

The model parameter specifies the AI model used for generating the artwork. It is crucial as it determines the underlying capabilities and style of the generated images. The choice of model can significantly impact the artistic quality and characteristics of the output.

conditioning

The conditioning parameter refers to the positive guidance applied during the sampling process. It helps steer the generation towards desired features or styles, ensuring that the output aligns with the artist's vision.

nag_negative

The nag_negative parameter is used to apply negative conditioning, which helps in suppressing unwanted features or styles in the generated image. This parameter is essential for achieving a balanced aesthetic by minimizing the influence of undesired elements.

nag_scale

The nag_scale parameter controls the intensity of the negative guidance. With a default value of 5.0, it can range from 0.0 to 100.0, allowing artists to adjust the strength of the negative influence to achieve the desired artistic effect.

nag_tau

The nag_tau parameter, with a default value of 2.5, ranges from 1.0 to 10.0. It influences the temporal aspect of the negative guidance, affecting how quickly the negative influence is applied during the sampling process.

nag_alpha

The nag_alpha parameter, ranging from 0.0 to 1.0 with a default of 0.25, determines the blending factor between positive and negative guidance. It allows artists to fine-tune the balance between desired and undesired elements in the final image.

nag_sigma_end

The nag_sigma_end parameter, with a default value of 0.0 and a range from 0.0 to 20.0, controls the endpoint of the sigma schedule for negative guidance. This parameter affects the smoothness and transition of the negative influence throughout the sampling process.

latent_image

The latent_image parameter represents the initial latent space representation of the image. It serves as the starting point for the sampling process, and its characteristics can influence the final output's style and quality.

NAGCFGGuider Output Parameters:

GUIDER

The GUIDER output is the primary result of the NAGCFGGuider node. It encapsulates the configured guidance settings that will be applied during the sampling process. This output is crucial for ensuring that the generated images adhere to the specified artistic direction and quality.

NAGCFGGuider Usage Tips:

  • Experiment with different nag_scale values to find the optimal balance between positive and negative guidance for your specific artistic goals.
  • Adjust the nag_alpha parameter to fine-tune the blending of desired and undesired elements, allowing for more nuanced control over the final image's aesthetic.
  • Utilize the nag_tau parameter to control the temporal application of negative guidance, which can help in achieving smoother transitions and more cohesive artistic styles.

NAGCFGGuider Common Errors and Solutions:

Error: "Invalid model input"

  • Explanation: This error occurs when the specified model is not compatible or incorrectly configured.
  • Solution: Ensure that the model parameter is set to a valid and supported AI model for the node.

Error: "Conditioning parameters missing"

  • Explanation: This error indicates that the required conditioning inputs are not provided.
  • Solution: Verify that both positive and negative conditioning parameters are correctly specified and not left empty.

Error: "Invalid nag_scale value"

  • Explanation: This error arises when the nag_scale parameter is set outside its allowable range.
  • Solution: Adjust the nag_scale value to be within the specified range of 0.0 to 100.0.

Error: "Latent image not provided"

  • Explanation: This error occurs when the latent_image input is missing or improperly configured.
  • Solution: Ensure that a valid latent image is provided as input to the node, as it is essential for the sampling process.

NAGCFGGuider Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-NAG-Extended
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

NAGCFGGuider